Implementation and Comparison of Machine Learning Algorithms for Recognition of Fingerspelling in Indian Sign Language
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2017, Vol 5, Issue 5
Abstract
Communication is the biggest hurdle faced by the hearing and speech impaired in leading a normal life. In this context, Sign Language is the most prominent means of communication. Machine learning and Computer Vision is an integral part of today’s computing world. This research paper proposes a Machine Learning based system to recognize fingerspelling gestures present in Indian Sign Language. Edge Frequency technique is chosen for Feature Extraction. The system was implemented using Aforge.NET framework. A comparative analysis of the Machine Learning Algorithms consisting of Support Vector Machine (SVM), K- Nearest Neighbor (KNN), Adaptive Naïve Bayes Classifier (ANBC), Decision Tree (DT) and Random Forests (RF) is performed to find out which algorithm is the most suitable to recognize ISL. Comparison is done based on validation accuracies and confusion matrices obtained. The accuracy for KNN was found to be 97.44% while SVM and ANBC have an accuracy of 96.15% and 82.05% respectively.
Authors and Affiliations
Nikhil Aatrei M, Shreyas H N, Sumesh S. Iyer, Gowranga K H, R Bhakthavathsalam
Integration of the ASR Toolkit Kaldi into a Domoticz Home Automation System
This paper presents the design and the implementation of an interface between Kaldi, automatic speech recognition toolkit, and a home automation system. This interface is based on Open Platform communication (OPC) protoc...
Evaluation of Tools and Techniques for the Generation of Warning Alerts: A Survey Paper
Quality assurance is a key factor for the improvement of an organizational behaviour. It is quite challenging to enhance an organizational performance without realising internal errors and mistakes done by its employees....
Handengineered Features vs Automated Features for Arabic Handwriting Recognition
This work aims to compare the learning features with Convolutional Neural Networks (CNNs) and the handcrafted features. In order to determine the relevant features among of those kinds. We consider our previous baseline...
Creatinine, Urea and Uric Acid in Hospitalized Patients with and Without Hyperglycemia Analysis using Generalized Additive Model
Hyperglycemia is an important risk factor for heart disease and premature mortality. In hospitalized patients, it is related to an increase in morbidity and development of other disease like kidney disease. To evaluate t...
The Adept K-Nearest Neighbour Algorithm - An optimization to the Conventional K-Nearest Neighbour Algorithm
This research aims to study the efficiency of a well-known classification algorithm, K-Nearest Neighbour, and suggest a new classification method, an optimised version than one of the existing classification method. The...